Reinforcement Learning for Transit Signal Priority with Priority Factor

doi:10.3390/smartcities7050111

Reinforcement Learning for Transit Signal Priority with Priority Factor

2024-10-06

0

OA

AI

DOI：10.3390/smartcities7050111

原文链接

原文求助

摘要

En 中文

Highlights What are the main findings? Effective Reduction of Bus Travel Times: The study's proposed transit signal priority (TSP) control system that incorporates a priority factor (PF) significantly reduces average travel times for buses-17% in the arterial network and 25% in the grid network. Mitigation of Conflicting Requests: The RL-based TSP with PF effectively resolves conflicting priority requests when multiple buses approach an intersection from different directions. Minimal Impact on Passenger Cars: While the average travel time for passenger cars increased (by up to 12% in the arterial network and 7% in the grid network), the impact is not significant compared to the improvements in bus travel times. Dynamic Assignment of PF: The PF can be dynamically assigned based on the number of passengers on each bus, enhancing the system's adaptability to varying traffic conditions. Longer Cycle Length and Signal Splits: An increase in buses with higher PF leads to longer cycle lengths and extended signal phase durations for directions with buses. What is the implication of the main finding? Improved Public Transit Efficiency: The findings suggest that integrating advanced control strategies like RL and dynamic PFs can enhance the efficiency of public transportation systems, making them more appealing and potentially increasing ridership. Balanced Traffic Management: The study indicates a feasible approach for balancing the needs of both transit and non-transit users at signalized intersections, which is crucial for urban mobility and reducing overall congestion. Scalability and Adaptability: The ability to dynamically adjust the PF based on passenger load suggests that this approach can be tailored to different traffic conditions and demands, making it adaptable for various urban environments. Future Research Directions: The findings underscore the need for further exploration into real-time PF determination and the integration of additional factors (like passenger waiting times) to enhance the operational efficiency and reliability of transit systems.Abstract Public transportation has been identified as a viable solution to mitigate traffic congestion. Transit signal priority (TSP) control, which is widely used at signalized intersections, has been recognized as a practical strategy to improve the efficiency and reliability of bus operations. However, traditional TSP control may fall short of efficiency and is facing several challenges of negative externalities for non-transit users and the need to handle conflicting priority requests. Recent studies have proposed the use of reinforcement learning (RL) methods to identify efficient traffic signal control (TSC). Some of these studies on RL-based TSC have incorporated the concept of max-pressure (MP), which is a maximal weight-matching algorithm to minimize queue sizes. Nevertheless, the existing RL-based TSC methods focus on private vehicles and cannot adequately distinguish between buses and private vehicles. In prior research, RL-based control has been implemented within the context of bus rapid transit (BRT) systems. This study proposes a novel RL-based TSC strategy that leverages the MP concept and extends it to incorporate TSP control. This is the first implementation of RL-based TSP control within the mixed-traffic road network. A significant innovation of this research is the introduction of the priority factor (PF), which is designed to prioritize bus movements at signalized intersections. The proposed RL-based TSP with PF control seeks to balance the competing objectives of enhancing bus operations while mitigating adverse impacts on non-transit users. To evaluate the performance of the proposed TSP method with the PF mechanism, simulations were conducted on an arterial and a grid network under dynamic traffic conditions. The simulation results demonstrated that the proposed TSP with PF not only reduces bus travel times and resolves conflicts between priority requests but also does not make a significant negative impact on passenger car operations. Furthermore, the PF can be dynamically assigned according to the number of passengers on each bus, suggesting the potential for the proposed approach to be applied in various traffic management scenarios.

Keyword:

transit signal priority

reinforcement learning

traffic signal control

max-pressure control

priority factor

Reinforcement Learning for Transit Signal Priority with Priority Factor

摘要

期刊

机构

引用论文